PUFF: An expert system for interpretation of pulmonary function data

Aikins, Janice S.; Kunz, John C.; Shortliffe, Edward H.; Fallat, Robert J.

doi:10.1016/0010-4809(83)90021-6

Cited by 220 publications

(58 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, a great deal of work has been done to combine expert systems and simulation methods in various problem areas and for different purposes (Delaney and Vaccari, 1989;Elzas, 1986;Fujiwara and Sakaguchi, 1986;Groen et al, 1986;Lehmann, 1987). In our design, we have also utilized such a combination.…”

Section: Figure 2 Level Of Abstraction In the Description Of A Patiementioning

confidence: 98%

“…QUATEMBER task easier. However, the contemporary expert systems in the field of pulmonary diseases (Aikins, 1983;Aikins et al, 1983;Kar et al, 1987) cannot handle temporal changes, since they are based solely on a "snapshot" approach to the patient's assessment. Hence, these systems cannot assist the physician in performing the particularly time-consuming tasks that follow:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of an Expert System for Chronic Obstructive Lung Disease

Quatember

1990

Cybernetics and Systems

View full text Add to dashboard Cite

Section: Figure 2 Level Of Abstraction In the Description Of A Patiementioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Development of an Expert System for Chronic Obstructive Lung Disease

Quatember

1990

Cybernetics and Systems

View full text Add to dashboard Cite

“…Hubert and Stuart Dreyfus (1986) report that PUFF (see Aikins et aL 1983) is used in this way. The expert user quickly recognises the eases where the system's advice is correct, and saves time because the advice already is nicely printed ready to be forwarded as the expert's own conclusion.…”

Section: Tools For An Expertmentioning

confidence: 99%

Evaluating expert system prototypes

Sørgaard

1991

AI & Soc

View full text Add to dashboard Cite

There is a disparity between the multitude of apparently successful expert system prototypes and the scarcity of expert systems in real everyday use. Modern tools make it deceptively easy to make reasonable prototypes, but these prototypes are seldom made subject to serious evaluation. Instead the development team confronts their product with a set of cases, and the primary evaluation criterion is the percentage of correct answers: we are faced with a "95% syndrome". Other aspects related to the use of the system are almost ignored. There is still a long way to go from a promising prototype to a final system.It is maintained in the article that a useful test must be performed by future users in a situation that is as realistic as possible. If this is not done claims of usefulness cannot be justified. It is also stated that prototyping does not make "traditional" analysis and design obsolete, although the contents of these activities will change.In order to discuss the effects of using the systems a distinction between expert systems as media, tools and experts is proposed.

show abstract

“…Articial intelligence approaches to medicine started with knowledge-based systems, constructed from knowledge provided by h uman experts, not data. Beginning with the expert systems of the seventies (MYCIN [Shortlie, 1976], PUFF [Aikins et al, 1982]), followed by Bayesian systems of the late eighties and early nineties (ACORN [Wyatt, 1989], PATHFINDER [Heckerman et al, 1992]), these knowledge-based systems generated much e n thusiasm. But there are very few such actual systems in routine clinical use.…”

Section: Introductionmentioning

confidence: 99%

Dementia Screening with Machine Learning Methods

Shankle¹,

Mani²,

Pazzani³

et al. 1997

Intelligent Data Analysis in Medicine and Pharmacology

View full text Add to dashboard Cite

Machine learning algorithms were applied to an electronic patient database generated by the UC Irvine Alzheimer's clinic to learn the simplest and most accurate patient parameters that would discriminate 244 very mildly demented from 198 normally aging subjects. Attributes included age, sex and education plus responses to the Functional Activities Questionnaire, the Mini-Mental Status and Blessed Orientation, Memory and Concentration tests. The Machine learning algorithms included decision tree learners(C4.5, CART), rule inducers(C4.5Rules, FOCL) and naive B a yes. Stepwise Logistic Regression was used to compare results. The sample was randomly split into training and testing sets, and the results were validated over 30 runs. Although the Functional Activities Questionnaire has been used since 1980, the Machine learning algorithms were the rst to identify that a single attribute, measuring forgetfulness, equaled or exceeded the accuracy of any other scoring method of this test. Post hoc inspection of the odds ratios obtained by Stepwise Logistic Regression conrmed this nding. The application of Machine learning has identied an extremely simple, yet accurate screen for very mild dementia.

show abstract

PUFF: An expert system for interpretation of pulmonary function data

Cited by 220 publications

References 2 publications

Development of an Expert System for Chronic Obstructive Lung Disease

Development of an Expert System for Chronic Obstructive Lung Disease

Evaluating expert system prototypes

Dementia Screening with Machine Learning Methods

Contact Info

Product

Resources

About